Apparatus program and method for data property recognition

Abstract

A data property recognition apparatus, includes a storage unit; a model data acquisition processor acquiring a plurality of model sets of data entries, each data entry individually representing an identified property common to the model set and being of a data type common to the model set; a feature vector generation processor receiving an input set of data entries, recognizing a data type common to the input set of data entries from among a plurality of supported data types, selecting a set of statistical characteristics representing the input set of data entries in dependence upon the recognised data type, generating a value of each of the selected set of statistical characteristics from the input set of data entries, and outputting a feature vector composed of the generated values of statistical characteristics.

Description

CROSS-REFERENCE TO RELATED APPLICATION[0001]The application is based upon and claims the benefit of priority of prior German patent application no. 102016220771.7, filed Oct. 21, 2016, the entirety of which is herein incorporated by reference.FIELD[0002]This application lies in the field of data science, and in particular relates to the automation of reconciliation of data entries from multiple data sources.BACKGROUND[0003]Data scientists spend time organizing and cleaning data, which time could be better-spent on procedures such as modelling or data mining. Standardization bodies, such as the World Wide Web Consortium (W3C), have worked for many years on proposing formats and best practices to facilitate data publication and sharing. However, not all data providers publish their data according to standards. Moreover, most standards focus on the syntax of the data model and forget about the data semantics. This often results in semantic interoperability problems when data from diffe...

AI Technical Summary

Benefits of technology

[0017]Advantageously, the updating of the feature vectors improves the quality of recognition with use of the reference set of feature vectors for recognition.

Problems solved by technology

However, not all data providers publish their data according to standards.

This often results in semantic interoperability problems when data from different sources are exchanged and merged, e.g. when two datasets refer to the same data property using different names.

The identification of data properties in a dataset it is complex and time-consuming when proper metadata is not available.

Images